© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2728
    Prev
    Next
    INDEX
    Explanations

    mapper mapping AutoMapper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    刷新
    0.44
    焕
    0.37
     clustering
    0.37
    labeled
    0.37
    Labeled
    0.36
     सेतु
    0.36
     Automatic
    0.35
    だと思う
    0.35
     तुम
    0.35
    ēng
    0.35
    POSITIVE LOGITS
     perl
    0.42
     созда
    0.38
    IndexPath
    0.37
     Juj
    0.37
     reconna
    0.37
    纹
    0.36
    amba
    0.36
     план
    0.35
     иска
    0.35
     ister
    0.35
    Activations Density 0.000%

    No Known Activations